This image demonstrates the character consistency capabilities of an image generation model. On the left, there are three input images featuring distinct characters: a fluffy bipedal creature in a hat, a small orange monster, and a smiling sheep in a party hat. To the right, a grid of six generated images shows these same characters interacting in a forest setting, depicting a narrative sequence where they work together to build and eventually enjoy a small wooden cabin.

Official Google DeepMind example. Published gallery preview; not generated by PixZoo. Separate original reference images were not supplied by the official gallery; upload the required references before reuse.

Prompt:

Create a funny 6 part story with these 3 fluffy friends building a tree house. The story is thrilling throughout with emotional highs and lows and is ending in a happy moment. Keep the attire and identity consistent of all 3 characters, but their expressions and angles should vary throughout all 6 images. Make sure to only have one of each character in each image. Generate 6 images one at a time. Each image should be a separate output in 16:9 format.